{"id":"W7015310510","doi":"","title":"A Study of Augmentation-Sensitivity in Reinforcement Learning","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Reinforcement; Control (management); Action (physics); Stability (learning theory)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001890266,0.0007169135,0.0009746144,0.001240567,0.000637272,0.0001519464,0.001240535,0.0004539804,0.0000391862],"category_scores_gemma":[0.0009516393,0.0008367227,0.0002027817,0.001705104,0.00002664456,0.001094886,0.0005487204,0.001997216,0.00006048896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008889593,"about_ca_system_score_gemma":0.0001530335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009566623,"about_ca_topic_score_gemma":0.00249567,"domain_scores_codex":[0.9940846,0.00081456,0.001669853,0.001228421,0.00149801,0.0007045666],"domain_scores_gemma":[0.9963267,0.0005289588,0.001281719,0.001198586,0.0005077161,0.0001562924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001366682,0.0005144273,0.0008150784,0.0004887236,0.0002967404,0.0001864759,0.0003234244,0.8944274,0.004011381,0.05731658,0.000002226423,0.04148083],"study_design_scores_gemma":[0.04530298,0.01874208,0.1241287,0.01616209,0.002356676,0.0001130084,0.03897922,0.480841,0.2179136,0.01632768,0.02159021,0.01754278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9224552,0.0000406618,0.0005174701,0.000008805034,0.001483915,0.001912333,0.00001261413,0.000310786,0.07325824],"genre_scores_gemma":[0.9843128,0.00005625131,0.001355923,0.0000635806,0.00001270247,0.0001408126,0.000245444,0.00006047497,0.01375196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4135865,"threshold_uncertainty_score":0.9994084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02194920132953579,"score_gpt":0.2696648351070748,"score_spread":0.2477156337775391,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}